1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
| import os
import sys
import getopt
import requests
import random
import re
import html2text
from bs4 import BeautifulSoup
useragents = [
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
]
def jinashu(url):
headers = {
'Host': 'www.jianshu.com',
'Referer': 'https://www.jianshu.com/',
'User-Agent': random.choice(useragents)
}
html = requests.get(url,headers=headers).text
soup = BeautifulSoup(html,"html5lib")
title = soup.find_all("title")[0].get_text()
article = str(soup.find_all("div",class_="show-content")[0])
article = re.sub('(src=")|(data-original-src=")','src="https:',article)
pwd = os.getcwd()
dirpath = pwd + '/jianshu/'
write2md(dirpath,title,article)
print(title+"下载完成....")
def csdn(url):
headers = {
'Host': 'blog.csdn.net',
'Referer': 'http://blog.csdn.net/',
'User-Agent': random.choice(useragents)
}
html = requests.get(url,headers=headers).text
soup = BeautifulSoup(html,'html5lib')
title = soup.find_all('title')[0].get_text()
article = str(soup.find_all('article')[0])
pwd = os.getcwd()
dirpath = pwd + '/CSDN/'
write2md(dirpath,title,article)
print(title+"下载完成....")
def zhihu(url):
headers = {
'Host': 'zhuanlan.zhihu.com',
'Referer': 'https://www.zhihu.com/',
'User-Agent': random.choice(useragents)
}
html = requests.get(url,headers=headers).text
soup = BeautifulSoup(html,'html5lib')
title = soup.find_all('title')[0].get_text()
article = str(soup.find_all('div',class_='Post-RichText')[0])
pwd = os.getcwd()
dirpath = pwd + '/ZhiHu/'
write2md(dirpath,title,article)
print(title+"下载完成....")
def doelse(url):
headers = {
'User-Agent': random.choice(useragents)
}
res = requests.get(url=url ,headers=headers)
h = html2text.HTML2Text()
h.ignore_links = False
soup = BeautifulSoup(res.text,'html5lib')
title = soup.title.text
html = str(soup.body)
article = h.handle(html)
pwd = os.getcwd()
dirpath = pwd + '/Else/'
if not os.path.exists(dirpath):
os.makedirs(dirpath)
pwd = os.getcwd()
dirpath = pwd + '/ELSE/'
write2md(dirpath,title,article)
print(title+"下载完成....")
"""
传入文件路径，title，article
"""
def write2md(dirpath,title,article):
h2md = html2text.HTML2Text()
h2md.ignore_links = False
article = h2md.handle(article)
if not os.path.exists(dirpath):
os.makedirs(dirpath)
with open(dirpath+title+'.md','w',encoding="utf8") as f:
lines = article.splitlines()
for line in lines:
if line.endswith('-'):
f.write(line)
else:
f.write(line+"\n")
def main(argv):
try:
opts,args = getopt.getopt(argv,"hu:",["url"])
except getopt.GetoptError:
print("python html2md.py -u <url>")
for opt,arg in opts:
if opt == "-h":
print("python html2md.py -u <url>")
sys.exit(2)
elif opt in ("-u", "-url"):
print()
checkSite(arg)
else:
print("python html2md.py -u <url>")
def checkSite(url):
if url.find('csdn') != -1:
csdn(url)
elif url.find('jianshu') != -1:
jinashu(url)
elif url.find('zhihu') != -1:
zhihu(url)
else:
doelse(url)
if __name__ == "__main__":
main(sys.argv[1:])
|